Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation

TL;DR

This paper introduces a counterfactual reasoning framework for path-based explainable recommendation systems, replacing traditional attention weights with learnable explainable weights to improve interpretability and reliability.

Contribution

It proposes a novel counterfactual reasoning approach for explainability in recommendations, addressing the instability and misalignment issues of attention-based explanations.

Findings

The method outperforms attention-based models in explanation stability.

It provides more human-aligned explanations.

Experimental results confirm the effectiveness of the approach.

Abstract

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.